Not in the top 1,000 by GitHub stars

Tubo2333/obsidian-knowledge-brain

AI agent skill that remembers every technical decision & bug fix across sessions — and learns from them. v4.0, MIT. | 跨会话记忆的AI编程助手知识大脑

Engineering

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

`SKILL.md`

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

de83d3a5a9cc → de83d3a5a9cc

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → de83d3a5a9cc

No earlier version was observed for comparison.

Compare on GitHub

View on GitHub Add to my skills

Verified commit de83d3a5a9ccd724b3e504c72b72001242c50061

101GitHub stars

0stars in 7 days

1skill in this repository

0commits in 30 days

Heat

0.3

Star growth, last 7 daysNot available
Star growth, last 24 hoursNot available
Rank movement, last 7 daysNot available
Commits, last 30 daysNot available
Accounts asking about it through MCP, last 7 daysNot available
Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

30-day change not yet available: not enough history.

Individual skills in this repository

obsidian-knowledge-brain /

How it works

When your agent uses it

What it loads into context

Frontmatter

0 tokens

Always available to the agent

SKILL.md

4,220 tokens

When the skill is activated

Reference documents

17,946 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

0. Critical Rules / 关键规则 (Priority 0)
0a. Prerequisites / 环境要求
0b. Sandbox Boundary / 沙箱边界
0c. Known Limitations / 已知局限 (Agent: read before acting)
1. Phase Detection / 相位检测 (Execute FIRST)
2. Phase A · Framework Bootstrap / 框架播种
3. T1-T4 Trigger Contracts / 触发契约
4. Annotation MVA Standards / 标注最低可行标准
5. Cold Start Protocol / 冷启动协议
6. File Manifest / 文件清单
7. Install & Config / 安装与配置
8. FAQ / 常见问题
9. Bilingual Terminology / 中英术语对照

Scripts executed separately

scripts/__init__.py
scripts/analyzer.py
scripts/backup.py
scripts/benchmark.py
scripts/compiler.py
scripts/config.py
scripts/global_atoms.py
scripts/install.py
scripts/keyword_index.py
scripts/link_validator.py
scripts/maintainer.py
scripts/pre_action.py
scripts/reformat_tables.py
scripts/reporter.py
scripts/runner.py
scripts/score_sessions.py
scripts/session_close.py
scripts/session_harvester.py
scripts/session_start.py
scripts/setup.py
scripts/validate_frontmatter.py

Files

.github/ISSUE_TEMPLATE/bug_report.mddoc668 bytes
.github/ISSUE_TEMPLATE/feature_request.mddoc633 bytes
.github/PULL_REQUEST_TEMPLATE.mddoc548 bytes
.gitignoreasset29 bytes
CHANGELOG.mddoc4,664 bytes
LICENSEasset1,082 bytes
README.mddoc13,389 bytes
SKILL.mdcore16,497 bytes
description.mddoc583 bytes
references/domain-registry.mddoc2,228 bytes
references/error-taxonomy.mddoc3,346 bytes
references/phase-a-bootstrap.mddoc5,326 bytes
references/platform-guide.mddoc3,209 bytes
references/quickstart.mddoc3,773 bytes
references/root-cause-kb.mddoc3,665 bytes
references/t1-session-start.mddoc4,088 bytes
references/t2-session-end.mddoc7,441 bytes
references/t3-periodic-check.mddoc4,567 bytes
references/troubleshooting.mddoc5,660 bytes
scripts/__init__.pyruns47 bytes
scripts/analyzer.pyruns20,845 bytes
scripts/backup.pyruns5,827 bytes
scripts/benchmark.pyruns16,616 bytes
scripts/compiler.pyruns16,414 bytes
scripts/config.example.yamlasset733 bytes
scripts/config.pyruns2,486 bytes
scripts/global_atoms.pyruns15,904 bytes
scripts/install.pyruns11,206 bytes
scripts/keyword_index.pyruns10,709 bytes
scripts/link_validator.pyruns3,943 bytes
scripts/maintainer.pyruns25,621 bytes
scripts/pre_action.pyruns11,730 bytes
scripts/reformat_tables.pyruns2,464 bytes
scripts/reporter.pyruns27,551 bytes
scripts/requirements.txtdoc167 bytes
scripts/runner.pyruns9,290 bytes
scripts/score_sessions.pyruns8,167 bytes
scripts/session_close.pyruns11,911 bytes
scripts/session_harvester.pyruns25,067 bytes
scripts/session_start.pyruns14,871 bytes
scripts/setup.pyruns17,147 bytes
scripts/validate_frontmatter.pyruns4,599 bytes
templates/decision.template.mddoc905 bytes
templates/pitfall.template.mddoc1,118 bytes
templates/project.template.mddoc1,097 bytes
templates/rule.template.mddoc953 bytes

Read SKILL.md

# Obsidian Knowledge Brain v4.0 / Obsidian 知识大脑 v4.0

**Schema**: 4.0 | **Lines**: ≤200 | **Load**: Always (if skill active)
**Platforms**: **Claude Code** — full auto (hooks + cron). **Cursor / Gemini CLI / Codex** — manual trigger (type "收尾" to save, "诊断" to bootstrap). Requires an AI Agent with file read/write. Not designed for plain-terminal or Agent-free use. / CC 全自动，其他平台需手动输入口令触发。

**Upgrade from v2.0**: zero vault dependency (无 vault 依赖), project-local `.claude/` storage. Obsidian is now optional — open your project folder as a vault for knowledge graph visualization. / Obsidian 现为可选——将项目文件夹作为 vault 打开即可获得知识图谱可视化。

**What this does / 它做什么**: Every time you debug an error or make a technical decision with an AI agent, that knowledge vanishes when the session ends. This skill **remembers** — it captures your decisions and error fixes across sessions, builds a searchable knowledge base, and evolves project rules automatically. A personal project librarian that learns from every conversation. / 每次和 AI 编程解决了 bug、做了技术决策，下次对话就忘了。这个 Skill 帮你**记住**——自动捕获每次会话的决策和错误，构建可检索的知识库，持续进化项目规则。一个从每次对话中学习的项目图书管理员。

**Obsidian?** Not required. v4.0 stores knowledge as `.md` files in your agent directory. Open your project as an Obsidian vault to browse the knowledge graph — purely optional. See §0a. / 非必需。用 Obsidian 打开项目文件夹即可浏览知识图谱——完全可选。

→ **First time?** See `references/quickstart.md` (5-minute walkthrough / 5分钟上手).

## 0. Critical Rules / 关键规则 (Priority 0)

View the complete source on GitHub

Skills included

Repository facts

License: MIT
Created: Jun 12, 2026
Last pushed: Jul 2, 2026
Forks: 9
Open issues: 1
Project activity: Slowing

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 6, 2026

No broad tool permissions
No dangerous shell commands
13 network referencesin 4 files: README.md:3 scripts/analyzer.py:315 scripts/config.py:47 and 1 more
No hidden or obfuscated text
No instruction overrides
21 executable scriptsin 21 files: scripts/__init__.py:1 scripts/analyzer.py:1 scripts/backup.py:1 and 18 more
10 references to secretsin 4 files: scripts/config.py:39 scripts/session_harvester.py:26 scripts/analyzer.py:272 and 1 more
No requests to vote in Hot

Show all 44 signals by file

`README.md`

Network accessline 3

![Version](https://img.shields.io/badge/version-4.0.0-blue)

Network accessline 4

![License](https://img.shields.io/badge/license-MIT-green)

Network accessline 5

![Platform](https://img.shields.io/badge/platform-Claude%20Code%20%7C%20Cursor%20%7C%20Gemini%20%7C%20Codex-lightgrey)

Network accessline 65

git clone https://github.com/Tubo2333/obsidian-knowledge-brain.git .claude/skills/obsidian-knowledge-brain/

`scripts/init.py`

Executable scriptline 1
```
Executable file
```

`scripts/analyzer.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 272
```
[Credential-related source omitted]
```

Network accessline 315

for attempt in range(max_retries):         try:             resp = requests.post(

Network accessline 316

try:             resp = requests.post(                 f"{api_cfg['base_url']}/messages",

Network accessline 317
```
resp = requests.post(
```

`scripts/backup.py`

Executable scriptline 1
```
Executable file
```

`scripts/benchmark.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/compiler.py`

Executable scriptline 1
```
Executable file
```

`scripts/config.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 39
```
[Credential-related source omitted]
```
Access to secretsline 40
```
[Credential-related source omitted]
```
Access to secretsline 41
```
[Credential-related source omitted]
```
Access to secretsline 45
```
[Credential-related source omitted]
```

Network accessline 47

env.get('ANTHROPIC_BASE_URL') or                      settings.get('ANTHROPIC_BASE_URL') or                      'https://api.anthropic.com/v1'),

Network accessline 48

settings.get('ANTHROPIC_BASE_URL') or                      'https://api.anthropic.com/v1'),         'model': (api_cfg.get('model') or

Network accessline 49
```
'https://api.anthropic.com/v1'),
```
Access to secretsline 60
```
[Credential-related source omitted]
```

`scripts/global_atoms.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/install.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/keyword_index.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/link_validator.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/maintainer.py`

Executable scriptline 1
```
Executable file
```

`scripts/pre_action.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/reformat_tables.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/reporter.py`

Executable scriptline 1
```
Executable file
```

`scripts/runner.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/score_sessions.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/session_close.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/session_harvester.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Access to secretsline 26
```
[Credential-related source omitted]
```
Access to secretsline 204
```
[Credential-related source omitted]
```
Access to secretsline 635
```
[Credential-related source omitted]
```

Network accessline 651

import socket     try:         s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)

Network accessline 652

try:         s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)         s.settimeout(2)

Network accessline 653

s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)

`scripts/session_start.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Access to secretsline 397
```
[Credential-related source omitted]
```

`scripts/setup.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/validate_frontmatter.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Declared and executed: 1 fact

Contacts api.anthropic.com, which SKILL.md, the README and the plugin manifest do not mentionscripts/config.py:49High confidence

Signal confidence: 44 facts

Network access in prose of documentationREADME.md:3Low confidence
Network access in prose of documentationREADME.md:4Low confidence
Network access in prose of documentationREADME.md:5Low confidence
Network access in code of documentationREADME.md:65Low confidence
Executable script in a comment of a file that runsscripts/__init__.py:1Low confidence
Executable script in prose of a file that runsscripts/analyzer.py:1Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/analyzer.py:272Low confidence
Network access in code of a file that runsscripts/analyzer.py:315High confidence
Network access in code of a file that runsscripts/analyzer.py:316High confidence
Network access in code of a file that runsscripts/analyzer.py:317High confidence
Executable script in prose of a file that runsscripts/backup.py:1Low confidence
Executable script in code of a file that runsscripts/benchmark.py:1High confidence
Executable script in prose of a file that runsscripts/compiler.py:1Low confidence
Executable script in prose of a file that runsscripts/config.py:1Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/config.py:39Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/config.py:40Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/config.py:41Low confidence
Access to secrets in code of a file that runsscripts/config.py:45High confidence
Network access in code of a file that runsscripts/config.py:47High confidence
Network access in code of a file that runsscripts/config.py:48High confidence
Network access in code of a file that runsscripts/config.py:49High confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/config.py:60Low confidence
Executable script in code of a file that runsscripts/global_atoms.py:1High confidence
Executable script in code of a file that runsscripts/install.py:1High confidence
Executable script in code of a file that runsscripts/keyword_index.py:1High confidence
Executable script in code of a file that runsscripts/link_validator.py:1High confidence
Executable script in prose of a file that runsscripts/maintainer.py:1Low confidence
Executable script in code of a file that runsscripts/pre_action.py:1High confidence
Executable script in code of a file that runsscripts/reformat_tables.py:1High confidence
Executable script in prose of a file that runsscripts/reporter.py:1Low confidence
Executable script in code of a file that runsscripts/runner.py:1High confidence
Executable script in code of a file that runsscripts/score_sessions.py:1High confidence
Executable script in code of a file that runsscripts/session_close.py:1High confidence
Executable script in code of a file that runsscripts/session_harvester.py:1High confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/session_harvester.py:26Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/session_harvester.py:204Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/session_harvester.py:635Low confidence
Network access in code of a file that runsscripts/session_harvester.py:651High confidence
Network access in code of a file that runsscripts/session_harvester.py:652High confidence
Network access in code of a file that runsscripts/session_harvester.py:653High confidence
Executable script in code of a file that runsscripts/session_start.py:1High confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/session_start.py:397Low confidence
Executable script in code of a file that runsscripts/setup.py:1High confidence
Executable script in code of a file that runsscripts/validate_frontmatter.py:1High confidence

Works with

Agent compatibility, from the files in this repository
Agent	Status	Evidence
Claude Code	Unknown	No evidence
Codex	Unknown	No evidence
Cursor	Unknown	No evidence
Gemini CLI	Unknown	No evidence
GitHub Copilot	Unknown	No evidence
OpenCode	Unknown	No evidence

Native The repository ships a manifest, folder or frontmatter field for this agent.
Compatible A standard SKILL.md that this agent can read.
Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

Tubo2333/obsidian-knowledge-brain

History

SKILL.md

Share this page

Heat

Stars over time

Individual skills in this repository

How it works

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

Skills included

Repository facts

Before you install

README.md

scripts/__init__.py

scripts/analyzer.py

scripts/backup.py

scripts/benchmark.py

scripts/compiler.py

scripts/config.py

scripts/global_atoms.py

scripts/install.py

scripts/keyword_index.py

scripts/link_validator.py

scripts/maintainer.py

scripts/pre_action.py

scripts/reformat_tables.py

scripts/reporter.py

scripts/runner.py

scripts/score_sessions.py

scripts/session_close.py

scripts/session_harvester.py

scripts/session_start.py

scripts/setup.py

scripts/validate_frontmatter.py

How the signals fit together

Works with

You might also use

GAURAV-1313/codecall

doccker/cc-use-exp

PSPDFKit-labs/nutrient-agent-skill

blader/humanizer

GanyuanRan/Aegis

first-fluke/oh-my-agent

`SKILL.md`

`README.md`

`scripts/init.py`

`scripts/analyzer.py`

`scripts/backup.py`

`scripts/benchmark.py`

`scripts/compiler.py`

`scripts/config.py`

`scripts/global_atoms.py`

`scripts/install.py`

`scripts/keyword_index.py`

`scripts/link_validator.py`

`scripts/maintainer.py`

`scripts/pre_action.py`

`scripts/reformat_tables.py`

`scripts/reporter.py`

`scripts/runner.py`

`scripts/score_sessions.py`

`scripts/session_close.py`

`scripts/session_harvester.py`

`scripts/session_start.py`

`scripts/setup.py`

`scripts/validate_frontmatter.py`